test(consistency): exercise the Azure backend against Azurite

Adds an Azurite service and a scenario that audits the Azure backend
through `?storage=azurite`. It is the only coverage of that code path in
the tree: `AzureBlobBackend` has unit tests for its name parser and
ordering, but nothing else speaks the protocol, and a paid account is
not an option for CI. Azurite implements the real Blob REST API, so this
exercises SharedKey signing, prefix/marker paging, and the 256-way shard
walk with its termination.

## Harness

`docker-compose.test.yml` gains an azurite service on 10000 (tmpfs, so
it dies with the stack). `spawn-db.sh` provisions the container itself,
because `AzureBlobBackend::initialize` verifies rather than creates —
signed by hand with curl + openssl rather than pulling a ~700 MB `az`
image for one PUT. Two traps are commented there: the account key is
base64 but HMAC wants raw bytes, and the canonicalized resource repeats
the account name (`/{acc}/{acc}/{container}`) because the emulator puts
in the path what real Azure puts in the host. Getting that wrong yields
403, not a hint.

The `azurite` entry is declared in `server.env` but never activated, so
the suite's active backend stays local and only this file reaches Azure.

## What it asserts, and what it cannot

A failure surfaces as `ok: false`, because an enumeration error now
fails the run rather than degrading to a per-row probe.

It deliberately asserts no finding count. The container starts empty and
the job's grace window is an hour, so a freshly-uploaded blob is skipped
in both directions by design — an audit here can only report zero, and
"zero findings" would pass whether enumeration worked or returned
nothing. The one positive assert, `scanned_count != 0`, therefore sits
on the local control, which does hold blobs; `scanned_count` accumulates
via `checkpoint`, which the empty-page early return skips.

## No cutover, deliberately

Putting real bytes in the container means `backend_migration
?storage=azurite`, which hangs on the first blob: `head_check` issues a
~40-byte ranged GET, `azure_core` 0.21 attaches
`x-ms-range-get-content-crc64` to anything under 4 MiB, Azurite 500s,
and the deterministic error is retried forever while
`migration_readonly` refuses writes app-wide. The full chain and the
rejected workaround are in the file header. The scenario is still
ordered last in `run.sh` — it is the only one needing a second service,
and the cutover comes back there once the official SDK lands.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Edouard Vanbelle
2026-09-02 19:24:46 +02:00
parent 2b52d233f0
commit 04e0df0c89
6 changed files with 404 additions and 4 deletions
+29
View File
@@ -14,3 +14,32 @@ services:
interval: 2s
timeout: 5s
retries: 10
# Azure Blob Storage emulator. Speaks the real Blob REST API, so it is
# the only way to exercise the Azure backend without an account — and
# the account it does ship is the fixed, publicly-documented dev pair
# (`devstoreaccount1` + the well-known key), so nothing here is a
# credential worth protecting.
#
# Blob service only: `--blobHost` with no queue/table, since the backend
# uses blobs exclusively and the other two would just be open ports.
#
# tmpfs for the same reason postgres uses it — a run must start from an
# empty container, or a previous run's blobs read as orphans in the very
# audit this exists to test.
azurite-test:
image: mcr.microsoft.com/azure-storage/azurite:3.36.0
command: azurite-blob --blobHost 0.0.0.0 --blobPort 10000 --location /data --skipApiVersionCheck
ports:
- "10000:10000"
tmpfs:
- /data
healthcheck:
# Azurite answers 400 to an unauthenticated root GET, which is proof
# enough that the HTTP listener is up — the SDK handshake is what
# validates credentials, and that happens later in the backend's
# own `initialize`.
test: ["CMD-SHELL", "nc -z 127.0.0.1 10000 || exit 1"]
interval: 2s
timeout: 5s
retries: 15
+19 -1
View File
@@ -42,7 +42,7 @@ OXICLOUD_NEXTCLOUD_ENABLED=true
# `s3_stub` is declared but never activated — it lets storage_config.hurl
# assert the entries table has more than one row without needing a
# real S3 backend.
OXICLOUD_STORAGE_ENTRIES=local_main,s3_stub
OXICLOUD_STORAGE_ENTRIES=local_main,s3_stub,azurite
OXICLOUD_STORAGE_local_main_BACKEND=local
OXICLOUD_STORAGE_s3_stub_BACKEND=s3
OXICLOUD_STORAGE_s3_stub_S3_BUCKET=oxicloud-test-stub
@@ -51,6 +51,24 @@ OXICLOUD_STORAGE_s3_stub_S3_ENDPOINT_URL=http://127.0.0.1:9999
OXICLOUD_STORAGE_s3_stub_S3_ACCESS_KEY=stub
OXICLOUD_STORAGE_s3_stub_S3_SECRET_KEY=stub
# `azurite` — a REAL, reachable Azure backend, unlike `s3_stub` above.
# It points at the Azurite emulator started by spawn-db.sh, which speaks
# the actual Blob REST API, so this is the only way to exercise the Azure
# path without an account.
#
# Declared but NOT activated: the active backend stays local_main, so the
# rest of the suite is untouched. Tests reach it explicitly through
# `?storage=azurite` on the jobs that accept an entry name — which is
# exactly what that parameter was added for.
#
# The credentials are Azurite's fixed, publicly-documented development
# pair. They are in every Microsoft quickstart; nothing here is secret.
OXICLOUD_STORAGE_azurite_BACKEND=azure
OXICLOUD_STORAGE_azurite_AZURE_ACCOUNT_NAME=devstoreaccount1
OXICLOUD_STORAGE_azurite_AZURE_ACCOUNT_KEY=Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw==
OXICLOUD_STORAGE_azurite_AZURE_CONTAINER=oxicloud-test
OXICLOUD_STORAGE_azurite_AZURE_ENDPOINT_URL=http://127.0.0.1:10000/devstoreaccount1
RUST_LOG="warn,audit=info,sqlx::migrate=info"
#RUST_LOG="warn,audit=info,oxicloud::quota=debug"
#RUST_LOG=debug
+82 -1
View File
@@ -52,7 +52,57 @@ wait_for_postgres_ready() {
exit 1
}
echo "[setup] Starting test postgres..."
# Create the blob container Azurite serves.
#
# `AzureBlobBackend::initialize` VERIFIES the container exists and fails
# with a 404 if it does not — it deliberately does not create one, since
# auto-creating would turn a typo'd container name into a silently
# working empty container. So the harness provisions it, exactly as an
# operator would in production.
#
# Signed by hand rather than shelling out to the Azure CLI: `az` would
# mean pulling a ~700 MB image into every CI run to issue one PUT. This
# needs only curl and openssl, both already required.
#
# Two things make this fiddly enough to be worth commenting:
# * The key is base64 and HMAC needs raw bytes, so it is decoded and
# re-encoded as hex for `-macopt hexkey:`.
# * The canonicalized resource repeats the account name —
# `/{account}/{account}/{container}` — because the emulator puts the
# account in the URL path where real Azure puts it in the host. This
# is the classic Azurite signing trap; getting it wrong yields 403,
# not a hint.
#
# Idempotent by result: a second run gets 409 ContainerAlreadyExists,
# which is success for our purposes.
create_azurite_container() {
local acc=devstoreaccount1
local cont=oxicloud-test
# Azurite's fixed development key — hardcoded in the image, published
# by Microsoft, and valid against nothing but a local emulator.
local key='Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw=='
local ver=2021-08-06
local date_hdr hexkey sts sig code
date_hdr=$(LC_ALL=C TZ=GMT date '+%a, %d %b %Y %H:%M:%S GMT')
hexkey=$(printf '%s' "$key" | base64 -d | od -An -tx1 | tr -d ' \n')
# Twelve leading empty lines are the unused standard headers
# (Content-*, Date, If-*, Range) the SharedKey scheme requires in
# fixed positions.
sts="PUT\n\n\n\n\n\n\n\n\n\n\n\nx-ms-date:${date_hdr}\nx-ms-version:${ver}\n/${acc}/${acc}/${cont}\nrestype:container"
sig=$(printf '%b' "$sts" | openssl dgst -sha256 -mac HMAC -macopt "hexkey:${hexkey}" -binary | base64)
code=$(curl -s -o /dev/null -w '%{http_code}' -X PUT \
-H "x-ms-date: ${date_hdr}" \
-H "x-ms-version: ${ver}" \
-H "Authorization: SharedKey ${acc}:${sig}" \
"http://127.0.0.1:10000/${acc}/${cont}?restype=container" 2>/dev/null)
case "$code" in
201) echo "[setup] Azurite container '${cont}' created." ;;
409) echo "[setup] Azurite container '${cont}' already exists." ;;
*) echo "[setup] WARNING: could not create Azurite container '${cont}' (HTTP ${code}) — Azure-backed tests will fail." >&2 ;;
esac
}
echo "[setup] Starting test postgres + azurite..."
docker compose -f "$COMPOSE_FILE" down -v 2>/dev/null || true
docker compose -f "$COMPOSE_FILE" up -d
echo "[setup] Waiting for postgres on port 5433..."
@@ -60,3 +110,34 @@ wait_for_port 127.0.0.1 5433
echo "[setup] Waiting for postgres to accept queries..."
wait_for_postgres_ready
echo "[setup] Postgres is ready."
# Azurite backs the `azurite` storage entry, which `backend_consistency`
# audits via `?storage=azurite`. Only a port wait: the entry is declared
# but never activated, so nothing in the suite touches it until a test
# names it, and by then the listener has had the whole server boot to
# settle. A failure here should not take down a run that mostly does not
# use it — so this warns rather than exits, and the Azure test fails on
# its own terms with a clearer message than "setup timed out".
#
# Its own loop rather than `wait_for_port`: that helper calls `exit 1` on
# timeout, and `exit` inside a function ends the script whatever context
# it was called from — so wrapping it in an `if` would not degrade, it
# would just fail later and less clearly.
echo "[setup] Waiting for azurite on port 10000..."
azurite_deadline=$(( $(date +%s) + 30 ))
until nc -z 127.0.0.1 10000 2>/dev/null; do
if [[ $(date +%s) -ge $azurite_deadline ]]; then
echo "[setup] WARNING: azurite did not come up — Azure-backed tests will fail." >&2
break
fi
sleep 0.5
done
if nc -z 127.0.0.1 10000 2>/dev/null; then
# Port open only means the listener is up — NOT that the tests can use
# it. Saying "ready" here was misleading: the container was still
# missing, so the first Azure job failed with a 404 while setup had
# already reported success. `create_azurite_container` is what makes
# the claim true, so it is the one that gets to announce it.
echo "[setup] Azurite listening; provisioning container..."
create_azurite_container
fi